Seongchan Kim

Seongchan Kim, Woojeong Jin, Sangbeom Lim et al.

Referring video object segmentation (RVOS) requires tracking and segmenting an object throughout a video according to a given natural language expression, demanding both complex motion understanding and the alignment of visual representations with language descriptions. Given these challenges, the recently proposed Segment Anything Model 2 (SAM2) emerges as a potential candidate due to its ability to generate coherent segmentation mask tracks across video frames, and provide an inherent spatio-temporal objectness in its object token representations. In this paper, we introduce SOLA (Selection by Object Language Alignment), a novel framework that leverages SAM2 object tokens as compact video-level object representations, which are aligned with language features through a lightweight track selection module. To effectively facilitate this alignment, we propose an IoU-based pseudo-labeling strategy, which bridges the modality gap between SAM2 representations with language features. Extensive experiments show that SOLA achieves state-of-the-art performance on the MeViS dataset and demonstrate that SOLA offers an effective solution for RVOS. Our project page is available at: https://cvlab-kaist.github.io/SOLA.

Woojeong Jin, Seongchan Kim, Jaeho Lee et al.

Referring video object segmentation (RVOS) aims to segment objects in a video described by a natural language expression. However, most existing approaches focus on segmenting only the referred object (typically the actor), even when the expression clearly describes an interaction involving multiple objects with distinct roles. For instance, "A throwing B" implies a directional interaction, but standard RVOS segments only the actor (A), neglecting other involved target objects (B). In this paper, we introduce Interaction-aware Referring Video Object Segmentation (InterRVOS), a novel task that focuses on the modeling of interactions. It requires the model to segment the actor and target objects separately, reflecting their asymmetric roles in an interaction. This task formulation enables fine-grained understanding of object relationships, as many video events are defined by such relationships rather than individual objects. To support this task, we propose a new evaluation protocol that separately evaluates actor and target segmentation, enabling more accurate assessment of the model's ability to distinguish and segment actor and target roles. We also present InterRVOS-127K, a large-scale dataset with over 127K automatically annotated expressions, including interaction expressions annotated with distinct masks for actor and target objects. Furthermore, we develop ReVIOSa, an MLLM-based architecture that introduces interaction-aware special tokens and leverages an attention mask loss to enhance role-specific segmentation. Extensive experiments show that ReVIOSa not only outperforms existing baselines on our proposed InterRVOS-127K evaluation set, but also achieves strong performance on standard RVOS benchmarks. Our project page is available at: https://cvlab-kaist.github.io/InterRVOS.

Siyoon Jin, Seongchan Kim, Dahyun Chung et al.

Video DiTs have advanced video generation, yet they still struggle to model multi-instance or subject-object interactions. This raises a key question: How do these models internally represent interactions? To answer this, we curate MATRIX-11K, a video dataset with interaction-aware captions and multi-instance mask tracks. Using this dataset, we conduct a systematic analysis that formalizes two perspectives of video DiTs: semantic grounding, via video-to-text attention, which evaluates whether noun and verb tokens capture instances and their relations; and semantic propagation, via video-to-video attention, which assesses whether instance bindings persist across frames. We find both effects concentrate in a small subset of interaction-dominant layers. Motivated by this, we introduce MATRIX, a simple and effective regularization that aligns attention in specific layers of video DiTs with multi-instance mask tracks from the MATRIX-11K dataset, enhancing both grounding and propagation. We further propose InterGenEval, an evaluation protocol for interaction-aware video generation. In experiments, MATRIX improves both interaction fidelity and semantic alignment while reducing drift and hallucination. Extensive ablations validate our design choices. Codes and weights will be released.

Sangbeom Lim, Seongchan Kim, Seungjun An et al.

Current benchmarks for video segmentation are limited to annotating only salient objects (i.e., foreground instances). Despite their impressive architectural designs, previous works trained on these benchmarks have struggled to adapt to real-world scenarios. Thus, developing a new video segmentation dataset aimed at tracking multi-granularity segmentation target in the video scene is necessary. In this work, we aim to generate multi-granularity video segmentation dataset that is annotated for both salient and non-salient masks. To achieve this, we propose a large-scale, densely annotated multi-granularity video object segmentation (MUG-VOS) dataset that includes various types and granularities of mask annotations. We automatically collected a training set that assists in tracking both salient and non-salient objects, and we also curated a human-annotated test set for reliable evaluation. In addition, we present memory-based mask propagation model (MMPM), trained and evaluated on MUG-VOS dataset, which leads to the best performance among the existing video object segmentation methods and Segment SAM-based video segmentation methods. Project page is available at https://cvlab-kaist.github.io/MUG-VOS.

Seungkyun Hong, Seongchan Kim, Minsu Joh et al.

Predicting unseen weather phenomena is an important issue for disaster management. In this paper, we suggest a model for a convolutional sequence-to-sequence autoencoder for predicting undiscovered weather situations from previous satellite images. We also propose a symmetric skip connection between encoder and decoder modules to produce more comprehensive image predictions. To examine our model performance, we conducted experiments for each suggested model to predict future satellite images from historical satellite images. A specific combination of skip connection and sequence-to-sequence autoencoder was able to generate closest prediction from the ground truth image.

Seongchan Kim, Seungkyun Hong, Minsu Joh et al.

Accurate rainfall forecasting is critical because it has a great impact on people's social and economic activities. Recent trends on various literatures show that Deep Learning (Neural Network) is a promising methodology to tackle many challenging tasks. In this study, we introduce a brand-new data-driven precipitation prediction model called DeepRain. This model predicts the amount of rainfall from weather radar data, which is three-dimensional and four-channel data, using convolutional LSTM (ConvLSTM). ConvLSTM is a variant of LSTM (Long Short-Term Memory) containing a convolution operation inside the LSTM cell. For the experiment, we used radar reflectivity data for a two-year period whose input is in a time series format in units of 6 min divided into 15 records. The output is the predicted rainfall information for the input data. Experimental results show that two-stacked ConvLSTM reduced RMSE by 23.0% compared to linear regression.

Seungkyun Hong, Seongchan Kim, Minsu Joh et al.

Advances in remote sensing technologies have made it possible to use high-resolution visual data for weather observation and forecasting tasks. We propose the use of multi-layer neural networks for understanding complex atmospheric dynamics based on multichannel satellite images. The capability of our model was evaluated by using a linear regression task for single typhoon coordinates prediction. A specific combination of models and different activation policies enabled us to obtain an interesting prediction result in the northeastern hemisphere (ENH).